Senior ML Engineer: Perception & Data Annotation Lead

Torc; Ann Arbor (MI); Hybrid; USD 199,200 - 298,800; Full time

Benefits offered by this job

Bonus component

Stock options

100% paid medical, dental, and vision

401K with match

Generous paid vacation

AD&D and Life Insurance

Job summary

Torc is seeking a data labeling and AI/ML specialist to join our autonomous trucking team in a role focused on offline perception, annotation, and model development. You will design and deploy object detection, tracking, and fusion modules using camera, lidar, and radar data, while guiding junior engineers and maintaining rigorous software practices.

Requirements include a PhD/masters with extensive experience in computer vision, deep learning, and ML tooling.

Qualifications

• Active Learning & Pseudo-labeling in Computer Vision and Deep Learning.
• Two of the following: 2D/3D Object Detection, Tracking, Sensor Fusion, Semantic Segmentation, SLAM, BEV.
• Scaled ML Operations (MLOps) and Tooling – ML Frameworks, experiment tracking, model registry, MLFlow, Weights and Biases, ML Metrics and Evaluation / Quality.
• Distributed machine learning frameworks - PyTorch, Lightning, Ray.
• Model Data Curation - Parquet data processing (PyArrow, Daft, Pandas, etc).
• Development Tools & Eco-System (at scale) - Proficiency in Python; Cloud-based environments; CI (GitHub Actions); Docker.

Responsibilities

• Design, implement, test and deploy offline object detection, tracking and fusion modules.
• Mentor and guide engineers within the group.
• Stay up to date with AI/ML developments for autonomous driving.
• Develop offline perception models and document code and processes.
• Define data ingestion, preparation, and governance for large data sets.
• Propose improvements aligned with strategy and operations.
• Measure and improve auto labeling quality.
• Provide data products and visualization support for customers.
• Evaluate technical advances to improve productivity and quality.

Skills

Active Learning & Pseudo-labeling

2D/3D Object Detection

Tracking

Sensor Fusion

Semantic Segmentation

SLAM

BEV

ML Operations (MLOps)

PyTorch

Python

Docker

GitHub Actions

ML Frameworks

Parquet processing (PyArrow, Daft, etc

Education

Bachelor’s Degree in Computer Science, Robotics, Electrical Engineering or related technical field

Master’s Degree in Computer Science, Robotics, Electrical Engineering or related technical field

Tools

Python

Docker

VDI

Cloud-based development environments

GitHub Actions

MLFlow

Weights & Biases

Job description

Torc is seeking a data labeling and AI/ML specialist to join our autonomous trucking team in a role focused on offline perception, annotation, and model development. You will design and deploy object detection, tracking, and fusion modules using camera, lidar, and radar data, while guiding junior engineers and maintaining rigorous software practices.

Requirements include a PhD/masters with extensive experience in computer vision, deep learning, and ML tooling.